期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2008
卷号：XXXVII Part B7
页码：909-914
出版社：Copernicus Publications
摘要：In machine learning, the preprocessing of the observations and the resulting features are one of the most important factors for the performance of the final system. In this paper, a robust approach to urban change detection for high resolution images is presented based on feature selection and machine learning. The rationale of the proposed approach is to improve the interclass variability by extracting change features of different types at different scales, to choose the informative change features by feature selection, to achieve the reliable results by machine learning. By taking advantages of feature selection and machine learning, the proposed approach is superior to the related methods in accuracy, efficiency and robustness. Experiments demonstrate the effectiveness and advantage of the proposed approach
关键词：Urban; Change Detection; High Resolution Images; Feature Selection; Machine Learning
